메뉴 건너뛰기
.. 내서재 .. 알림
소속 기관/학교 인증
인증하면 논문, 학술자료 등을  무료로 열람할 수 있어요.
한국대학교, 누리자동차, 시립도서관 등 나의 기관을 확인해보세요
(국내 대학 90% 이상 구독 중)
로그인 회원가입 고객센터 ENG
주제분류

추천
검색

논문 기본 정보

자료유형
학술저널
저자정보
박찬호 (계명대학교) 김성훈 (한양대학교)
저널정보
한국교육평가학회 교육평가연구 교육평가연구 제29권 제4호
발행연도
2016.12
수록면
697 - 713 (17page)

이용수

표지
📌
연구주제
📖
연구배경
🔬
연구방법
🏆
연구결과
AI에게 요청하기
추천
검색

초록· 키워드

오류제보하기
When multiple forms exist for a standardized educational test, a single scale should be maintained over administrations of the forms for test scores from each form to be interchangeably used, and fixed parameter calibration (FPC) has been a useful linking method when item response theory is used. If multiple skills or traits are necessary when solving a certain types of test items, multidimensional item response theory (MIRT) models are useful. This study proposed FPC as a linking method for MIRT. The model considered in this study is a two-parameter logistic MIRT model as a compensatory MIRT model. To examine how FPC functions for MIRT linking, a simulation analysis was conducted for a 50-item test with 1,000 examinees. The simulation factors were the number of common items, increased levels of ability means, and varying degrees of latent trait covariances. A Markov chain Monte Carlo estimation algorithm was employed for parameter estimation. As a result, item parameter recovery was acceptable overall. Item difficulty parameters were most accurately estimated, followed by item discrimination parameters, latent trait means, and latent trait variances-covariances. No systematic biases were observed although there was some variability across simulation conditions. Generally, the number of common items was the most influential factor for accurate estimation of item and person parameters, and the influences of the other conditions were minimal. The utility of the proposed method and directions for future research were also discussed.

목차

등록된 정보가 없습니다.

참고문헌 (22)

참고문헌 신청

함께 읽어보면 좋을 논문

논문 유사도에 따라 DBpia 가 추천하는 논문입니다. 함께 보면 좋을 연관 논문을 확인해보세요!

이 논문의 저자 정보

최근 본 자료

전체보기

댓글(0)

0